IEM Atlanta 2026 · BO3
result vs prediction
paiN#32 in the world · loss 1:2series probability
32%68%
probability at match start · final 1:2
GamerLegion#14 in the world · win 2:1The prediction was locked in using data as of the match start: map winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Map veto prediction
For each map — both teams' winrate over 3 months. The model guesses who bans it and who keeps it: teams remove maps where they are weaker and pull toward their strong ones.
Miragepossible decider
50%50%
paiN · 0 mapsnearly even +0%GamerLegion · 4 maps
NukepaiN pick
67%67%
paiN · 2 mapsnearly even +0%GamerLegion · 2 maps
AncientpaiN ban
50%67%
paiN · 0 mapsedge GamerLegion +17%GamerLegion · 2 maps
Dust2GamerLegion ban
50%50%
paiN · 2 mapsnearly even +0%GamerLegion · 0 maps
InfernoGamerLegion pick
50%50%
paiN · 0 mapsnearly even +0%GamerLegion · 2 maps
AnubisGamerLegion ban
40%50%
paiN · 1 mapedge GamerLegion +10%GamerLegion · 0 maps
OverpasspaiN ban
40%50%
paiN · 1 mapedge GamerLegion +10%GamerLegion · 0 maps
Most likely veto scenario
1. BanpaiN remove Ancient
2. BanGamerLegion remove Dust2
3. PickpaiN take Nuke
4. PickGamerLegion take Inferno
5. BanGamerLegion remove Anubis
6. BanpaiN remove Overpass
DeciderMirage (50% / 50%)
Prediction by map vs result
Probabilities were locked in using statistics as of the match start (map winrate over the 3 months before it). We compare against the actual result of each map.
Overpassprediction missed13:6
paiN 37%GamerLegion 63%
The model gave 63% on GamerLegion — the map was taken by paiN.
Nukeprediction missed6:13
paiN 53%GamerLegion 47%
The model gave 53% on paiN — the map was taken by GamerLegion.
Infernoprediction missed8:13
paiN 50%GamerLegion 50%
The model gave 50% on paiN — the map was taken by GamerLegion.
Model check result
Model favoriteGamerLegion · 68%
Series resultGamerLegion 1:2
Series predictioncorrect
Accuracy by map0 of 3